Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is clear. The description adds valuable non-annotation context: the scoring model is a transparent heuristic (not a proprietary black-box), and the endpoint's lack of per-user state. This discloses behavioral constraints that the schema and annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with high information density. The first sentence covers the purpose and scoring dimensions, the second reveals the heuristic nature, and the third provides the critical operational caveat. No filler words, no restating of parameter names that are already in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is mostly complete given the simplicity of the tool (single required param, no output schema, no nested objects). It covers purpose, exceptions, and parameter handling. Minor gap: it does not describe the scoring output format (e.g., numeric scores per dimension, an overall score, or qualitative feedback), which an agent may need to know to parse the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds important parameter semantics for 'brand_profile_id' (local-only, remote-unavailable, omit for stateless) and clarifies 'creative_text' meaning (prompt, script, ad copy, or concept). It does not add detail on 'channel' or 'audience', but the schema already describes them adequately, and the description adds value for the trickiest parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Score') and explicitly enumerates the resource types (creative prompt, script, ad concept) and the seven evaluation dimensions (hook strength, benefit clarity, product signal, CTA, channel fit, audience fit, brand fit). It further distinguishes itself from sibling tools like evaluate_design and score_page by clarifying the scoring is a transparent heuristic, not a proprietary model, which clarifies its unique purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage context: local brand profiles are not available on the hosted remote endpoint, and per-user state is a later phase. It instructs the agent to omit 'brand_profile_id' for stateless scoring, which is a clear when/how directive. This goes beyond implied usage and gives actionable selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.